Update app.py (#1)

- Update app.py (9a0f7e63c0fb52f17a2f278f0443c7bdef132c22)


Co-authored-by: Shreelakshmi <shree2216@users.noreply.huggingface.co>

app.py

@@ -1,72 +1,21 @@
 import gradio as gr
+import pandas as pd
 import cv2
 import numpy as np
-import tempfile
-import mediapipe as mp
-from sklearn.cluster import KMeans
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.preprocessing import LabelEncoder
 
-# Initialize mediapipe face mesh
-mp_face_mesh = mp.solutions.face_mesh
-face_mesh = mp_face_mesh.FaceMesh(static_image_mode=True)
-
-# Skin tone categories based on RGB intensity
-def classify_skin_tone(rgb_color):
-    r, g, b = rgb_color
-    brightness = (r + g + b) / 3
-    if brightness > 200:
-        return "Fair"
-    elif brightness > 120:
-        return "Medium"
-    else:
-        return "Deep"
-
-# Extract cheek region for skin tone detection
-def get_cheek_pixels(image, landmarks):
-    h, w, _ = image.shape
-    # Cheek landmark indices (approximation)
-    cheek_ids = [234, 93, 132, 58]  # Left cheek
-    pixels = []
-    for idx in cheek_ids:
-        pt = landmarks[idx]
-        x, y = int(pt.x * w), int(pt.y * h)
-        # Sample a small patch around each point
-        patch = image[max(0, y-2):min(h, y+2), max(0, x-2):min(w, x+2)]
-        if patch.size > 0:
-            pixels.extend(patch.reshape(-1, 3))
-    return np.array(pixels)
-
-# Main function
-def analyze_face(image):
-    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
-    results = face_mesh.process(image_rgb)
-
-    if not results.multi_face_landmarks:
-        return image, "No face detected"
-
-    landmarks = results.multi_face_landmarks[0].landmark
-    cheek_pixels = get_cheek_pixels(image, landmarks)
-
-    # Skin tone analysis using KMeans
-    kmeans = KMeans(n_clusters=1, random_state=0).fit(cheek_pixels)
-    dominant_color = kmeans.cluster_centers_[0].astype(int)
-    skin_tone = classify_skin_tone(dominant_color)
-
-    # Annotate image with skin tone
-    annotated = image.copy()
-    cv2.putText(annotated, f"Skin Tone: {skin_tone}", (30, 30),
-                cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-
-    return annotated, skin_tone
+# Load dataset function
+def load_dataset(file):
+    df = pd.read_excel(file)
+    return df.head()
 
 # Gradio interface
 iface = gr.Interface(
-    fn=analyze_face,
-    inputs=gr.Image(type="numpy", label="Capture your face"),
-    outputs=[
-        gr.Image(type="numpy", label="Processed Image"),
-        gr.Textbox(label="Detected Skin Tone")
-    ],
-    title="Face Skin Tone Detector"
+    fn=load_dataset,
+    inputs=gr.File(label="Upload Excel Dataset"),
+    outputs=gr.Dataframe(label="Preview of Dataset"),
+    title="Skin Tone Detector"
 )
 
-iface.launch()
+iface.launch()